© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 11064
    Prev
    Next
    INDEX
    Explanations

    phrases related to crime, investigations, and specific names or terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Murder" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srfAttach
    -0.76
     deaf
    -0.72
     slips
    -0.66
    umo
    -0.62
    idium
    -0.62
     mas
    -0.62
     deflect
    -0.62
     overboard
    -0.61
    bestos
    -0.61
    advertising
    -0.61
    POSITIVE LOGITS
    isher
    0.99
    ishers
    0.95
    erer
    0.91
    riter
    0.89
    erers
    0.88
    ers
    0.88
    rict
    0.87
    rup
    0.87
    erey
    0.86
    ered
    0.85
    Activations Density 0.016%

    No Known Activations